{"id":"W3046648263","doi":"","title":"Daydream: Accurately Estimating the Efficacy of Optimizations for {DNN} Training","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Profiling (computer programming); Software deployment; Artificial neural network; Software; Artificial intelligence; Machine learning; Graph; Dependency graph; Parallel computing; Computer engineering; Theoretical computer science; Software engineering; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006687071,0.0000909663,0.0001143727,0.00002891479,0.0002545803,0.00002700736,0.0009224843,0.00002768108,0.000004224803],"category_scores_gemma":[0.0001642301,0.00008357597,0.00007129103,0.0008863717,0.00007342091,0.0003444513,0.0001736743,0.00008635124,0.000007189986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001799314,"about_ca_system_score_gemma":0.00005212921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001873266,"about_ca_topic_score_gemma":0.000001235325,"domain_scores_codex":[0.999291,0.00002973054,0.0001336212,0.0003355306,0.00003811,0.0001719943],"domain_scores_gemma":[0.9986712,0.0006573497,0.0001460168,0.0003614694,0.0000815555,0.00008239788],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006888159,0.00001276387,0.0000316913,0.000004191509,0.000009358018,0.000001699614,0.0005386999,0.8104711,0.0001470071,0.1856968,0.0001078066,0.002971983],"study_design_scores_gemma":[0.0003465144,0.00003810896,0.00008609407,0.000006697869,0.00001738289,0.000001262825,0.00008917803,0.9930541,0.0003440746,0.005510808,0.0004155519,0.0000902402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0176676,0.00001107317,0.980214,0.001257374,0.00005067415,0.0002954986,0.000005751485,0.0001247458,0.0003732948],"genre_scores_gemma":[0.876399,0.000004276763,0.1232308,0.0002418167,0.00005143308,0.00000198044,0.000003329427,0.000007283511,0.00006010669],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8587313,"threshold_uncertainty_score":0.3408129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2144990876850486,"score_gpt":0.246582360473011,"score_spread":0.03208327278796241,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}